© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152534
    Prev
    Next
    INDEX
    Explanations

    dimensions and exterior dimensions

    np_acts-logits-general · gemini-2.5-flash-lite

    common phrases after words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     angiel
    0.51
     teplot
    0.49
    ⭒
    0.47
    狎
    0.47
     bpm
    0.46
     marít
    0.46
     ř
    0.46
     adı
    0.46
     pô
    0.45
     hongkong
    0.45
    POSITIVE LOGITS
    ks
    0.63
    t
    0.62
    partners
    0.59
    la
    0.58
    mult
    0.58
    4
    0.58
    len
    0.57
    fle
    0.57
    st
    0.57
    nt
    0.57
    Activations Density 0.000%

    No Known Activations